Paper Group ANR 409
Divergence-Free Shape Interpolation and Correspondence. Style and Content Disentanglement in Generative Adversarial Networks. Quantum-inspired sublinear classical algorithms for solving low-rank linear systems. Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints. Learning-induced cat …
Divergence-Free Shape Interpolation and Correspondence
| Title | Divergence-Free Shape Interpolation and Correspondence |
| Authors | Marvin Eisenberger, Zorah Lähner, Daniel Cremers |
| Abstract | We present a novel method to model and calculate deformation fields between shapes embedded in $\mathbb{R}^D$. Our framework combines naturally interpolating the two input shapes and calculating correspondences at the same time. The key idea is to compute a divergence-free deformation field represented in a coarse-to-fine basis using the Karhunen-Lo`eve expansion. The advantages are that there is no need to discretize the embedding space and the deformation is volume-preserving. Furthermore, the optimization is done on downsampled versions of the shapes but the morphing can be applied to any resolution without a heavy increase in complexity. We show results for shape correspondence, registration, inter- and extrapolation on the TOSCA and FAUST data sets. |
| Tasks | |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10417v2 |
| http://arxiv.org/pdf/1806.10417v2.pdf | |
| PWC | https://paperswithcode.com/paper/divergence-free-shape-interpolation-and |
| Repo | |
| Framework | |
Style and Content Disentanglement in Generative Adversarial Networks
| Title | Style and Content Disentanglement in Generative Adversarial Networks |
| Authors | Hadi Kazemi, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi |
| Abstract | Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in an unsupervised fashion and capture the most significant factors of the data variations. However, these approaches ignore the principle of content and style disentanglement in image generation, which means their learned latent code may alter the content and style of the generated images at the same time. This paper describes the Style and Content Disentangled GAN (SC-GAN), a new unsupervised algorithm for training GANs that learns disentangled style and content representations of the data. We assume that the representation of an image can be decomposed into a content code that represents the geometrical information of the data, and a style code that captures textural properties. Consequently, by fixing the style portion of the latent representation, we can generate diverse images in a particular style. Reversely, we can set the content code and generate a specific scene in a variety of styles. The proposed SC-GAN has two components: a content code which is the input to the generator, and a style code which modifies the scene style through modification of the Adaptive Instance Normalization (AdaIN) layers’ parameters. We evaluate the proposed SC-GAN framework on a set of baseline datasets. |
| Tasks | Image Generation |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.05621v1 |
| http://arxiv.org/pdf/1811.05621v1.pdf | |
| PWC | https://paperswithcode.com/paper/style-and-content-disentanglement-in |
| Repo | |
| Framework | |
Quantum-inspired sublinear classical algorithms for solving low-rank linear systems
| Title | Quantum-inspired sublinear classical algorithms for solving low-rank linear systems |
| Authors | Nai-Hui Chia, Han-Hsuan Lin, Chunhao Wang |
| Abstract | We present classical sublinear-time algorithms for solving low-rank linear systems of equations. Our algorithms are inspired by the HHL quantum algorithm for solving linear systems and the recent breakthrough by Tang of dequantizing the quantum algorithm for recommendation systems. Let $A \in \mathbb{C}^{m \times n}$ be a rank-$k$ matrix, and $b \in \mathbb{C}^m$ be a vector. We present two algorithms: a “sampling” algorithm that provides a sample from $A^{-1}b$ and a “query” algorithm that outputs an estimate of an entry of $A^{-1}b$, where $A^{-1}$ denotes the Moore-Penrose pseudo-inverse. Both of our algorithms have query and time complexity $O(\mathrm{poly}(k, \kappa, \A_F, 1/\epsilon),\mathrm{polylog}(m, n))$, where $\kappa$ is the condition number of $A$ and $\epsilon$ is the precision parameter. Note that the algorithms we consider are sublinear time, so they cannot write and read the whole matrix or vectors. In this paper, we assume that $A$ and $b$ come with well-known low-overhead data structures such that entries of $A$ and $b$ can be sampled according to some natural probability distributions. Alternatively, when $A$ is positive semidefinite, our algorithms can be adapted so that the sampling assumption on $b$ is not required. |
| Tasks | Recommendation Systems |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04852v1 |
| http://arxiv.org/pdf/1811.04852v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-inspired-sublinear-classical |
| Repo | |
| Framework | |
Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints
| Title | Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints |
| Authors | Coralia Cartis, Nick I. M. Gould, Philippe L. Toint |
| Abstract | We provide sharp worst-case evaluation complexity bounds for nonconvex minimization problems with general inexpensive constraints, i.e.\ problems where the cost of evaluating/enforcing of the (possibly nonconvex or even disconnected) constraints, if any, is negligible compared to that of evaluating the objective function. These bounds unify, extend or improve all known upper and lower complexity bounds for unconstrained and convexly-constrained problems. It is shown that, given an accuracy level $\epsilon$, a degree of highest available Lipschitz continuous derivatives $p$ and a desired optimality order $q$ between one and $p$, a conceptual regularization algorithm requires no more than $O(\epsilon^{-\frac{p+1}{p-q+1}})$ evaluations of the objective function and its derivatives to compute a suitably approximate $q$-th order minimizer. With an appropriate choice of the regularization, a similar result also holds if the $p$-th derivative is merely H"older rather than Lipschitz continuous. We provide an example that shows that the above complexity bound is sharp for unconstrained and a wide class of constrained problems, we also give reasons for the optimality of regularization methods from a worst-case complexity point of view, within a large class of algorithms that use the same derivative information. |
| Tasks | |
| Published | 2018-11-03 |
| URL | http://arxiv.org/abs/1811.01220v1 |
| http://arxiv.org/pdf/1811.01220v1.pdf | |
| PWC | https://paperswithcode.com/paper/sharp-worst-case-evaluation-complexity-bounds |
| Repo | |
| Framework | |
Learning-induced categorical perception in a neural network model
| Title | Learning-induced categorical perception in a neural network model |
| Authors | Christian Thériault, Fernanda Pérez-Gay, Dan Rivas, Stevan Harnad |
| Abstract | In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP). There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model. Whether CP is essential to categorisation or simply a by-product of it is not yet clear, but evidence is accumulating that CP can be induced by category learning. We provide a model for learning-induced CP as expansion and compression of distances in hidden-unit space in neural nets. Basic conditions from which the current model predicts CP are described, and clues as to how these conditions might generalize to more complex kinds of categorization begin to emerge. |
| Tasks | |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04567v1 |
| http://arxiv.org/pdf/1805.04567v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-induced-categorical-perception-in-a |
| Repo | |
| Framework | |
Student Beats the Teacher: Deep Neural Networks for Lateral Ventricles Segmentation in Brain MR
| Title | Student Beats the Teacher: Deep Neural Networks for Lateral Ventricles Segmentation in Brain MR |
| Authors | Mohsen Ghafoorian, Jonas Teuwen, Rashindra Manniesing, Frank-Erik de Leeuw, Bram van Ginneken, Nico Karssemeijer, Bram Platel |
| Abstract | Ventricular volume and its progression are known to be linked to several brain diseases such as dementia and schizophrenia. Therefore accurate measurement of ventricle volume is vital for longitudinal studies on these disorders, making automated ventricle segmentation algorithms desirable. In the past few years, deep neural networks have shown to outperform the classical models in many imaging domains. However, the success of deep networks is dependent on manually labeled data sets, which are expensive to acquire especially for higher dimensional data in the medical domain. In this work, we show that deep neural networks can be trained on much-cheaper-to-acquire pseudo-labels (e.g., generated by other automated less accurate methods) and still produce more accurate segmentations compared to the quality of the labels. To show this, we use noisy segmentation labels generated by a conventional region growing algorithm to train a deep network for lateral ventricle segmentation. Then on a large manually annotated test set, we show that the network significantly outperforms the conventional region growing algorithm which was used to produce the training labels for the network. Our experiments report a Dice Similarity Coefficient (DSC) of $0.874$ for the trained network compared to $0.754$ for the conventional region growing algorithm ($p < 0.001$). |
| Tasks | |
| Published | 2018-01-15 |
| URL | http://arxiv.org/abs/1801.05040v2 |
| http://arxiv.org/pdf/1801.05040v2.pdf | |
| PWC | https://paperswithcode.com/paper/student-beats-the-teacher-deep-neural |
| Repo | |
| Framework | |
Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs
| Title | Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs |
| Authors | Han Shao, Xiaotian Yu, Irwin King, Michael R. Lyu |
| Abstract | In linear stochastic bandits, it is commonly assumed that payoffs are with sub-Gaussian noises. In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0,1]$. We rigorously analyze the regret lower bound of LinBET as $\Omega(T^{\frac{1}{1+\epsilon}})$, implying that finite moments of order 2 (i.e., finite variances) yield the bound of $\Omega(\sqrt{T})$, with $T$ being the total number of rounds to play bandits. The provided lower bound also indicates that the state-of-the-art algorithms for LinBET are far from optimal. By adopting median of means with a well-designed allocation of decisions and truncation based on historical information, we develop two novel bandit algorithms, where the regret upper bounds match the lower bound up to polylogarithmic factors. To the best of our knowledge, we are the first to solve LinBET optimally in the sense of the polynomial order on $T$. Our proposed algorithms are evaluated based on synthetic datasets, and outperform the state-of-the-art results. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10895v2 |
| http://arxiv.org/pdf/1810.10895v2.pdf | |
| PWC | https://paperswithcode.com/paper/almost-optimal-algorithms-for-linear |
| Repo | |
| Framework | |
Uncertainty quantification of molecular property prediction using Bayesian neural network models
| Title | Uncertainty quantification of molecular property prediction using Bayesian neural network models |
| Authors | Seongok Ryu, Yongchan Kwon, Woo Youn Kim |
| Abstract | In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions. Despite the rapid increase in the use of state-of-the-art models and algorithms, deep neural network models often produce poor predictions in real applications because model performance is highly dependent on the quality of training data. In the field of molecular analysis, data are mostly obtained from either complicated chemical experiments or approximate mathematical equations, and then quality of data may be questioned.In this paper, we quantify uncertainties of prediction using Bayesian neural networks in molecular property predictions. We estimate both model-driven and data-driven uncertainties, demonstrating the usefulness of uncertainty quantification as both a quality checker and a confidence indicator with the three experiments. Our results manifest that uncertainty quantification is necessary for more reliable molecular applications and Bayesian neural network models can be a practical approach. |
| Tasks | Molecular Property Prediction |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1905.06945v1 |
| http://arxiv.org/pdf/1905.06945v1.pdf | |
| PWC | https://paperswithcode.com/paper/190506945 |
| Repo | |
| Framework | |
Recovering Loss to Followup Information Using Denoising Autoencoders
| Title | Recovering Loss to Followup Information Using Denoising Autoencoders |
| Authors | Lovedeep Gondara, Ke Wang |
| Abstract | Loss to followup is a significant issue in healthcare and has serious consequences for a study’s validity and cost. Methods available at present for recovering loss to followup information are restricted by their expressive capabilities and struggle to model highly non-linear relations and complex interactions. In this paper we propose a model based on overcomplete denoising autoencoders to recover loss to followup information. Designed to work with high volume data, results on various simulated and real life datasets show our model is appropriate under varying dataset and loss to followup conditions and outperforms the state-of-the-art methods by a wide margin ($\ge 20%$ in some scenarios) while preserving the dataset utility for final analysis. |
| Tasks | Denoising |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04664v1 |
| http://arxiv.org/pdf/1802.04664v1.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-loss-to-followup-information-using |
| Repo | |
| Framework | |
Weakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma Images
| Title | Weakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma Images |
| Authors | Mohammadhassan Izadyyazdanabadi, Evgenii Belykh, Claudio Cavallo, Xiaochun Zhao, Sirin Gandhi, Leandro Borba Moreira, Jennifer Eschbacher, Peter Nakaji, Mark C. Preul, Yezhou Yang |
| Abstract | Confocal Laser Endomicroscope (CLE) is a novel handheld fluorescence imaging device that has shown promise for rapid intraoperative diagnosis of brain tumor tissue. Currently CLE is capable of image display only and lacks an automatic system to aid the surgeon in analyzing the images. The goal of this project was to develop a computer-aided diagnostic approach for CLE imaging of human glioma with feature localization function. Despite the tremendous progress in object detection and image segmentation methods in recent years, most of such methods require large annotated datasets for training. However, manual annotation of thousands of histopathological images by physicians is costly and time consuming. To overcome this problem, we propose a Weakly-Supervised Learning (WSL)-based model for feature localization that trains on image-level annotations, and then localizes incidences of a class-of-interest in the test image. We developed a novel convolutional neural network for diagnostic features localization from CLE images by employing a novel multiscale activation map that is laterally inhibited and collaterally integrated. To validate our method, we compared proposed model’s output to the manual annotation performed by four neurosurgeons on test images. Proposed model achieved 88% mean accuracy and 86% mean intersection over union on intermediate features and 87% mean accuracy and 88% mean intersection over union on restrictive fine features, while outperforming other state of the art methods tested. This system can improve accuracy and efficiency in characterization of CLE images of glioma tissue during surgery, augment intraoperative decision-making process regarding tumor margin and affect resection rates. |
| Tasks | Decision Making, Object Detection, Semantic Segmentation |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09428v2 |
| http://arxiv.org/pdf/1804.09428v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-learning-based-feature |
| Repo | |
| Framework | |
Fusing First-order Knowledge Compilation and the Lifted Junction Tree Algorithm
| Title | Fusing First-order Knowledge Compilation and the Lifted Junction Tree Algorithm |
| Authors | Tanya Braun, Ralf Möller |
| Abstract | Standard approaches for inference in probabilistic formalisms with first-order constructs include lifted variable elimination (LVE) for single queries as well as first-order knowledge compilation (FOKC) based on weighted model counting. To handle multiple queries efficiently, the lifted junction tree algorithm (LJT) uses a first-order cluster representation of a model and LVE as a subroutine in its computations. For certain inputs, the implementations of LVE and, as a result, LJT ground parts of a model where FOKC has a lifted run. The purpose of this paper is to prepare LJT as a backbone for lifted inference and to use any exact inference algorithm as subroutine. Using FOKC in LJT allows us to compute answers faster than LJT, LVE, and FOKC for certain inputs. |
| Tasks | |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00743v1 |
| http://arxiv.org/pdf/1807.00743v1.pdf | |
| PWC | https://paperswithcode.com/paper/fusing-first-order-knowledge-compilation-and |
| Repo | |
| Framework | |
VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Camera
| Title | VUNet: Dynamic Scene View Synthesis for Traversability Estimation using an RGB Camera |
| Authors | Noriaki Hirose, Amir Sadeghian, Fei Xia, Roberto Martin-Martin, Silvio Savarese |
| Abstract | We present VUNet, a novel view(VU) synthesis method for mobile robots in dynamic environments, and its application to the estimation of future traversability. Our method predicts future images for given virtual robot velocity commands using only RGB images at previous and current time steps. The future images result from applying two types of image changes to the previous and current images: 1) changes caused by different camera pose, and 2) changes due to the motion of the dynamic obstacles. We learn to predict these two types of changes disjointly using two novel network architectures, SNet and DNet. We combine SNet and DNet to synthesize future images that we pass to our previously presented method GONet to estimate the traversable areas around the robot. Our quantitative and qualitative evaluation indicate that our approach for view synthesis predicts accurate future images in both static and dynamic environments. We also show that these virtual images can be used to estimate future traversability correctly. We apply our view synthesis-based traversability estimation method to two applications for assisted teleoperation. |
| Tasks | Autonomous Vehicles |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08864v2 |
| http://arxiv.org/pdf/1806.08864v2.pdf | |
| PWC | https://paperswithcode.com/paper/vunet-dynamic-scene-view-synthesis-for |
| Repo | |
| Framework | |
Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey
| Title | Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey |
| Authors | Norah Asiri, Muhammad Hussain, Fadwa Al Adel, Nazih Alzaidi |
| Abstract | Diabetic retinopathy (DR) results in vision loss if not treated early. A computer-aided diagnosis (CAD) system based on retinal fundus images is an efficient and effective method for early DR diagnosis and assisting experts. A computer-aided diagnosis (CAD) system involves various stages like detection, segmentation and classification of lesions in fundus images. Many traditional machine-learning (ML) techniques based on hand-engineered features have been introduced. The recent emergence of deep learning (DL) and its decisive victory over traditional ML methods for various applications motivated the researchers to employ it for DR diagnosis, and many deep-learning-based methods have been introduced. In this paper, we review these methods, highlighting their pros and cons. In addition, we point out the challenges to be addressed in designing and learning about efficient, effective and robust deep-learning algorithms for various problems in DR diagnosis and draw attention to directions for future research. |
| Tasks | |
| Published | 2018-11-03 |
| URL | https://arxiv.org/abs/1811.01238v2 |
| https://arxiv.org/pdf/1811.01238v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-computer-aided-diagnosis |
| Repo | |
| Framework | |
Improving Dialogue Act Classification for Spontaneous Arabic Speech and Instant Messages at Utterance Level
| Title | Improving Dialogue Act Classification for Spontaneous Arabic Speech and Instant Messages at Utterance Level |
| Authors | AbdelRahim Elmadany, Sherif Abdou, Mervat Gheith |
| Abstract | The ability to model and automatically detect dialogue act is an important step toward understanding spontaneous speech and Instant Messages. However, it has been difficult to infer a dialogue act from a surface utterance because it highly depends on the context of the utterance and speaker linguistic knowledge; especially in Arabic dialects. This paper proposes a statistical dialogue analysis model to recognize utterance’s dialogue acts using a multi-classes hierarchical structure. The model can automatically acquire probabilistic discourse knowledge from a dialogue corpus were collected and annotated manually from multi-genre Egyptian call-centers. Extensive experiments were conducted using Support Vector Machines classifier to evaluate the system performance. The results attained in the term of average F-measure scores of 0.912; showed that the proposed approach has moderately improved F-measure by approximately 20%. |
| Tasks | Dialogue Act Classification |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1806.00522v1 |
| http://arxiv.org/pdf/1806.00522v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-dialogue-act-classification-for |
| Repo | |
| Framework | |
Splenomegaly Segmentation on Multi-modal MRI using Deep Convolutional Networks
| Title | Splenomegaly Segmentation on Multi-modal MRI using Deep Convolutional Networks |
| Authors | Yuankai Huo, Zhoubing Xu, Shunxing Bao, Camilo Bermudez, Hyeonsoo Moon, Prasanna Parvathaneni, Tamara K. Moyo, Michael R. Savona, Albert Assad, Richard G. Abramson, Bennett A. Landman |
| Abstract | The findings of splenomegaly, abnormal enlargement of the spleen, is a non-invasive clinical biomarker for liver and spleen disease. Automated segmentation methods are essential to efficiently quantify splenomegaly from clinically acquired abdominal magnetic resonance imaging (MRI) scans. However, the task is challenging due to (1) large anatomical and spatial variations of splenomegaly, (2) large inter- and intra-scan intensity variations on multi-modal MRI, and (3) limited numbers of labeled splenomegaly scans. In this paper, we propose the Splenomegaly Segmentation Network (SS-Net) to introduce the deep convolutional neural network (DCNN) approaches in multi-modal MRI splenomegaly segmentation. Large convolutional kernel layers were used to address the spatial and anatomical variations, while the conditional generative adversarial networks (GAN) were employed to leverage the segmentation performance of SS-Net in an end-to-end manner. A clinically acquired cohort containing both T1-weighted (T1w) and T2-weighted (T2w) MRI splenomegaly scans was used to train and evaluate the performance of multi-atlas segmentation (MAS), 2D DCNN networks, and a 3D DCNN network. From the experimental results, the DCNN methods achieved superior performance to the state-of-the-art MAS method. The proposed SS-Net method achieved the highest median and mean Dice scores among investigated baseline DCNN methods. |
| Tasks | Splenomegaly Segmentation On Multi-Modal Mri |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04045v1 |
| http://arxiv.org/pdf/1811.04045v1.pdf | |
| PWC | https://paperswithcode.com/paper/splenomegaly-segmentation-on-multi-modal-mri |
| Repo | |
| Framework | |
